#arg1= all y datapoints
#arg2= all x datapoints
#label these datapoints
#linewidth is the width of the line
#marker is the symbol used for plotting datapoints
#s is the size if the marker
plt.figure(1)
#arg1 flagsize=(w,h)
plt.subplot(nrows=x,ncols=y,figsize=(x,y)).set_axis_off()
#2 is the number of row to divide figure into
#1 is the number of col to divide figure into
#1 is the current active figure
plt.grid()
plt.legand()
plt.ylabel("")
plt.xlabel("")
plt.title("")
plt.show()
plt.axis(off)
plt.close()
#........................................................................
plt.imshow()
#arg:-
#X [m,n,3],[m,n,4],[m,n]
#cmap (matplotlib.colors.Colormap) (ignored if RBGA/RGB values are given)
#aspect (equals, auto) maintains the aspect ration (ie square pixels)
#interpolation
plt.imread()
#AUC Scores
from sklearn.metrics import roc_auc_score
from sklearn.metrics import classification_report
print("---Base Model---")
base_roc_auc = roc_auc_score(y_test, base_rate_model(X_test))
print("Base Rate AUC = %2.2f" % base_roc_auc)
print(classification_report(y_test, base_rate_model(X_test)))
print("---Logistic Model---")
logit_roc_auc = roc_auc_score(y_test, y_pred)
print("Logistic Rate AUC = %2.2f" % base_roc_auc)
print(classification_report(y_test, y_pred))
#Graphing
from sklearn.metrics import roc_curve
fpr, tpr, thresholds = roc_curve(y_test,
classifier.predict_proba(X_test)[:, 1])
plt.figure()
plt.plot(fpr, tpr, label='ROC Curve (area = %0.2f)' % logit_roc_auc)
plt.plot([0, 1], [0, 1], 'k--')
plt.xlim([0.0, 1.0])
plt.xlim([0.0, 1.05])
plt.xlabel('Flase Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Ralationship Between Flase Positive & True Positives')
plt.legand(loc='lower right')
plt.show()